MisinfoNepal

News aggregator and analysis platform of Nepal

PlatformHome FeedAbout UsSource RegistryResearch & PublicationsContact
MisinfoNepal
© 2026 MisinfoNepal. All Rights Reserved.Designed by MisinfoNepal
MisinfoNepal
Academic Publications & Benchmark Datasets

Research & Benchmarks

Peer-reviewed preprints, longitudinal news datasets, and computational NLP benchmarking tools created for low-resource Nepali language processing and media intelligence.

SORTED BY DATE: NEWEST PUBLISHED / SUBMITTED FIRST
Showing 2 Peer-Reviewed & Preprint DOI Publications
Preprint / Journal PaperMarch 3, 2026
DOI: 10.21203/rs.3.rs-8630749/v1

Ekantipur-15Y: A Longitudinal Benchmark Corpus and Semantic Analysis of Nepali News (2010 - 2025)

Diwash Mainali, Utsav MainaliResearch Square (Springer Nature)
Corpus Size109,704 Articles
Token Count14.3 Million Tokens
Temporal Span2010 – 2025 (15 Years)
Baseline Accuracy74.50% Linear SVM
109,704 unique Nepali news articles (14.3 Million tokens)Zipf's & Heap's Law linguistic validationSemantic event extraction (2015 Earthquake, COVID-19 pandemic)Linear SVM Baseline accuracy: 74.50%
Abstract & Methodology

This paper introduces Ekantipur-15Y, a long-scale longitudinal corpus of Nepali news articles spanning from 2010 to 2025. As Nepali is considered a low-resource language, the lack of a clean and temporally diverse dataset has been a barrier for the development of robust Natural Language Processing (NLP) models. We collected and cleaned 109,704 unique articles with approximately 14.3 million tokens from Ekantipur. The corpus is validated using Zipf's law confirming linguistic integrity and Heap's law demonstrating continuous growth of vocabulary without plateauing. Furthermore, the semantic analysis successfully detects major historical events in the context of Nepal (such as the 2015 earthquake and COVID-19), establishing a baseline text classification accuracy of 74.50% using Linear SVM.

View Publication / Dataset
Open Dataset & MetadataJanuary 4, 2026
DOI: 10.5281/zenodo.18145188

Ekantipur-15Y Metadata

Diwash MainaliZenodo (CERN Repository)
RepositoryCERN Zenodo Open Science
LicenseCC-BY 4.0 International
Temporal Metadata2010 – 2025 (15 Years)
Data FormatStructured JSON Metadata
15-year longitudinal publication temporal metadataCreative Commons Attribution 4.0 International (CC-BY 4.0)Indexed in CERN Zenodo Open Science Repository
Abstract & Methodology
View Publication / Dataset

News aggregator and analysis platform of Nepal

PlatformHome FeedAbout UsSource RegistryResearch & PublicationsContact
MisinfoNepal
© 2026 MisinfoNepal. All Rights Reserved.Designed by MisinfoNepal